Last updated: March 12, 2019
source_info <- read_csv("source_info.csv")
target_info <- read_csv("target_info.csv")
See here for an explanation on on the meaning of these mismatches.
df <- right_join(target_info, source_info,
by = c("source" = "source",
"target" = "target",
"year" = "year")) %>%
mutate(diff = abs(flow.x - flow.y)) %>%
mutate(dyad = str_c(source, " -> ", target))
df %>%
ggplot(aes(flow.x / 100, flow.y / 100, color = diff / 100)) +
geom_point(alpha = 0.6) +
geom_abline(slope = 1, intercept = 0, linetype = "dashed") +
geom_hline(yintercept = 0, alpha = 0.5, size = 0.5) +
scale_color_viridis_c(direction = -1, labels = scales::dollar) +
scale_y_continuous(labels = scales::dollar) +
scale_x_continuous(labels = scales::dollar) +
labs(x = "target info", y = "source info", caption = "(billions of US dollars)", color = "mismatch")
for (i in 2001:2012) {
print(df %>%
filter(year == i) %>%
group_by(year) %>%
filter(rank(-diff) <= 10) %>%
ggplot(aes(x = fct_reorder(dyad, diff), y = diff / 100)) +
geom_point() +
facet_wrap(~ year, scales = "free") +
coord_flip() +
scale_y_continuous(labels = scales::dollar) +
labs(x = NULL, y = "Size of mismatch", caption = "(billions of US dollars)")
)
}
wdi_varlist <- readRDS("wdi_data/wdi_varlist.RDS")
gdp <- readRDS("wdi_data/wdi_data.RDS") %>%
select(country, continent, year, NY.GDP.MKTP.CD) %>% ## GDP (current US$)
rename(gdp = NY.GDP.MKTP.CD) %>%
ungroup()
target_info <- target_info %>%
left_join(rename(gdp, source = country)) %>%
rename(source_gdp = gdp, source_continent = continent) %>%
left_join(rename(gdp, target = country)) %>%
rename(target_gdp = gdp, target_continent = continent)
## Joining, by = c("source", "year")
## Joining, by = c("target", "year")
source_info <- source_info %>%
left_join(rename(gdp, source = country)) %>%
rename(source_gdp = gdp, source_continent = continent) %>%
left_join(rename(gdp, target = country)) %>%
rename(target_gdp = gdp, target_continent = continent)
## Joining, by = c("source", "year")
## Joining, by = c("target", "year")
df <- right_join(target_info, source_info,
by = c("source" = "source",
"target" = "target",
"year" = "year",
"target_continent" = "target_continent",
"source_continent" = "source_continent",
"source_gdp" = "source_gdp",
"target_gdp" = "target_gdp")) %>%
mutate(diff = abs(flow.x - flow.y)) %>%
mutate(dyad = str_c(source, " -> ", target))
for (i in 2001:2012) {
print(df %>%
mutate(diff_w = (diff * 1e6 / target_gdp)) %>%
filter(year == i) %>%
drop_na() %>%
filter(rank(-diff_w) <= 10) %>%
ggplot(aes(x = fct_reorder(dyad, diff_w), y = diff_w)) +
geom_point() +
facet_wrap(~ year, scales = "free") +
coord_flip() +
scale_y_continuous(labels = scales::percent) +
labs(x = NULL, y = "Size of mismatch", caption = "(% of target country's GDP)")
)
}
DOUBLE CHECK THIS
for (i in 2001:2012) {
print(df %>%
mutate(diff_w = (diff * 1e6 / source_gdp)) %>%
filter(year == i) %>%
drop_na() %>%
filter(rank(-diff_w) <= 10) %>%
ggplot(aes(x = fct_reorder(dyad, diff_w), y = diff_w)) +
geom_point() +
facet_wrap(~ year, scales = "free") +
coord_flip() +
scale_y_continuous(labels = scales::percent) +
labs(x = NULL, y = "Size of mismatch", caption = "(% of source country's GDP)")
)
}
DOUBLE CHECK THIS
\[ ff_i = \frac{\text{in-degree}_i}{\text{GDP}_i} \]
for (i in 2001:2012) {
print(target_info %>%
mutate(ff = flow * 1e6 / target_gdp) %>%
group_by(target, year) %>%
summarise(m = sum(ff)) %>%
filter(year == i) %>%
ungroup() %>%
drop_na() %>%
filter(rank(-abs(m)) <= 10) %>%
ggplot(aes(x = reorder(target, m), y = m)) +
geom_point() +
facet_wrap(~ year, scales = "free") +
coord_flip() +
scale_y_continuous(labels = scales::percent) +
labs(x = NULL, y = "In-degree / GDP")
)
}